AI Video Producer

Plugin ai-video-producer from marketplace shotcowboystyle in shotcowboystyle/ai-plugins. Commands read from the repo's manifest — 1 month ago.

Skills (11)

• budget-estimator

  Estimate API costs for a planned pipeline or for an entire script before any generation runs. Reads pipeline SPEC.md(s), the storyboard, and `brief/tools-and-models.md`, then projects cost per shot and total — with a low / typical / high range that accounts for take iteration. Writes a budget report

• comfyui-export

  Export an AI-Video-Producer pipeline to ComfyUI workflow JSON — produce a workflow the user can load in ComfyUI to reproduce (or approximate) a hosted-API pipeline locally. Best-effort: maps fal/replicate model calls to equivalent ComfyUI checkpoints/LoRAs/samplers and flags stages that have no nati

• comfyui-import

  Import a ComfyUI workflow JSON (the API-format export from ComfyUI's "Save (API Format)" option, or the UI-format graph JSON) and turn it into an AI-Video-Producer pipeline SPEC plus stage runners. Maps Comfy nodes to pipeline stages, surfaces the model checkpoints and LoRAs needed, and flags nodes

• model-researcher

  Research what fal.ai and Replicate (and optionally other providers — Runway, Kling, Pika, Hedra, ElevenLabs, OpenAI) currently offer for a given workload — text-to-image, text-to-video, image-to-video, lip-sync, voice, upscaling, interpolation — and recommend the best-fit model for the project's bri

• recommend-model

  Intelligent, preference-driven model recommendation across fal.ai, Replicate, WaveSpeedAI, and MiniMax (Hailuo). Asks the user a short set of preference questions (workload, priority — quality vs speed vs cost, max budget per output, resolution/aspect/duration, NSFW tolerance, must-have features lik

• script-to-tts

  Reformat an existing script for a specific text-to-speech model (ElevenLabs, OpenAI TTS, Google, Azure, Hume, Chatterbox, etc.). Splits VO into model-friendly chunks, inserts pacing/emphasis/SSML markers where the model supports them, strips bracketed visual direction, normalises numbers/abbreviatio

• text-to-image-to-video

  Two-stage pipeline that generates a still image from a text prompt (Flux/SDXL/Imagen) then animates it into a video clip (Kling/Runway/Hailuo/Wan). Use when the user wants tight visual control over the opening frame before motion.

• text-to-video-direct

  Single-step text-to-video generation (Sora, Veo, Kling text mode, Hailuo). Use for quick exploratory shots or when motion is more important than precise framing.

• upscale-and-interpolate

  Post-processing chain — upscale a clip's resolution and/or interpolate frames for smoother motion. Run after a clip is selected but before final assembly.

• video-workspace-conventions

  Reference for the AI video production workspace — lifecycle phases, folder layout, naming conventions, and working principles. Loaded by the install-video-workspace command and consulted by other commands when they need to know where things live.

• voice-to-lip-sync

  Generate a voice take (ElevenLabs or similar) and lip-sync it to an existing video clip of a character speaking. Use for talking-head shots where the visual is already generated.

Slash commands (11)

• /ai-video-producer:assemble

  Propose an ffmpeg/edit plan to concatenate clips/edited/ into a rough cut in output/drafts/.

• /ai-video-producer:define-character

  Add a recurring character or subject with appearance and voice notes. Saves to characters/.

• /ai-video-producer:draft-script

  Produce a script draft from the brief. Saves to scripts/drafts/.

• /ai-video-producer:export-final

  Finalise the locked draft — encode to spec, embed subtitles, write to output/final/.

• /ai-video-producer:install-video-workspace

  Scaffold the AI video production workspace (folder skeleton + project CLAUDE.md) into the current directory.

• /ai-video-producer:log-take

  Record a generated artefact's prompt, model, and parameters alongside the file. Usage: /log-take <artefact-path>

• /ai-video-producer:onboard

  Capture the creative brief, target spec, and model selection for this video project. Run this first.

• /ai-video-producer:promote-take

  Promote a raw take into clips/selected/ with rationale. Usage: /promote-take <raw-path>

• /ai-video-producer:run-pipeline

  Execute a predefined pipeline from pipelines/ for a given shot. Usage: /run-pipeline <pipeline-name> <shot-number>

• /ai-video-producer:setup-credentials

  One-time setup for fal.ai, Replicate, WaveSpeed, and MiniMax credentials, plus runner toolchain bootstrap. Writes ~/.config/ai-video-producer/.env, sources it from the user's shell profile, and installs the npm + pip dependencies needed by the SDK runners under runners/.

• /ai-video-producer:storyboard

  Break the locked script into a numbered shot list. Writes scripts/storyboards/ and timeline/shot-list.md.

Subagents (7)

• aspect-converter

  Use this agent to upscale and/or convert aspect ratio for video clips — e.g. taking a 720p 16:9 generation and producing a 1080p 9:16 vertical for Reels/Shorts/TikTok, or upscaling SD-era footage for inclusion alongside HD generations. Picks between resize-only, letterbox, blur-fill, smart-crop, and

• concatenator

  Use this agent when the user has produced video elements in parts (clips, segments, scenes, intro/outro, B-roll inserts) and is ready to join and render them into a single deliverable. Detects the host's GPU (NVIDIA / AMD / Intel / CPU-only) and picks the right ffmpeg encoder (NVENC / AMF / QSV / li

• normalizer

  Use this agent to normalise a set of video clips so they can be safely concatenated or compared — equalises loudness (EBU R128 / -16 LUFS by default), aligns sample rate / channel layout, conforms framerate and pixel format, and optionally applies basic colour-level normalisation (full↔limited range

• pipeline-builder

  Use this agent to turn an approved pipeline SPEC.md (produced by pipeline-scaffolder) into an executable pipeline — runnable scripts/configs that `/run-pipeline` can invoke. Generates per-stage runner files, parameter templates, an entry-point script, and a pipeline README. Wires up calls to fal/rep

• pipeline-repo-setup

  Use this agent to set up a private GitHub repository where the user versions reusable AI video pipelines across projects. Creates the repo via `gh`, scaffolds an opinionated structure (one folder per pipeline, shared model/cost reference, CHANGELOG, README), seeds it from any pipelines already prese

• pipeline-scaffolder

  Use this agent to scaffold a new generation pipeline definition inside an AI-Video-Producer workspace. Takes a high-level pipeline description (e.g. "text → image (Flux) → image-to-video (Kling) → upscale (Topaz)") and produces a structured pipeline spec under `pipelines/<name>/` with a SPEC.md, sta

• script-writer

  Use this agent to draft, revise, or polish a script for an AI video project. Operates inside an AI-Video-Producer workspace — reads `brief/creative-brief.md` and `brief/tools-and-models.md`, writes drafts to `scripts/drafts/`, iterates with the user until a draft is ready to promote to `scripts/fina

MCP servers (3)

• fal-ai

  connects to: https://mcp.fal.ai/mcp

• replicate

  runs: npx -y replicate-mcp

• minimax

  runs: uvx minimax-mcp -y

Similar plugins